Delays in Lung Cancer Diagnosis: Observations from a Tertiary Care Centre in Kerala, India.

Merin YohannanIntroduction Timely diagnosis of lung cancer is critical because treatment outcomes correspond to the stage of disease. This study identified patient and physician determined reasons for diagnostic delays. Materials and Method s This was an observational cross-sectional study, conducted at a tertiary care institution in South India, for 12 months. From 207 consecutively selected patients, with a presumptive lung cancer diagnosis, 150 were enrolled utilizing a prefixed questionnaire. The time intervals from appreciation of initial respiratory symptoms to a final tissue diagnosis were defined sequentially as approach interval, referral interval, and diagnostic interval and factors causing delay in each interval were identified. Results In a state with 100% literacy, the mean time to approach a doctor was 8 weeks (range: 0-336 days; SD: 7.95) with a delay seen in 52% of the study group. Referring a suspect lung cancer diagnosis to a specialist, took an average of 4.98 weeks (range: 1-26 weeks; SD: 5.64) with referral delays in 47.3% of patients. The mean diagnostic interval was 9.21 days (range: 3-41 days; SD: 7.18) and 16.7% of cases had diagnostic delays in spite of a definite procedure. Conclusion In a tuberculosis endemic location, empirical treatment with anti-tuberculosis therapy and prolonged antibiotic courses without serially monitoring the course of disease are responsible for referral delays. Also, 88.2% of the total females studied, presented late due to family and work pressures, fear of being stigmatized and being on prolonged home remedies. A wider dissemination and awareness on lung cancer are needed especially among females. A low threshold to reinvestigate and an early referral to a pulmonary or lung cancer specialist, when expected clinicoradiological improvement is lacking, in microbiologically negative tuberculosis should be highlighted.

Unsupervised landmark detection and classification of lung infection using transporter neural networks.

Supervised deep learning techniques have been very popular in medical imaging for various tasks of classification, segmentation, and object detection. However, they require a large number of labelled data which is expensive and requires many hours of careful annotation by experts. In this paper, an unsupervised transporter neural network framework with an attention mechanism is proposed to automatically identify relevant landmarks with applications in lung ultrasound (LUS) imaging. The proposed framework identifies key points that provide a concise geometric representation highlighting regions with high structural variation in the LUS videos. In order for the landmarks to be clinically relevant, we have employed acoustic propagation physics driven feature maps and angle-controlled Radon Transformed frames at the input instead of directly employing the gray scale LUS frames. Once the landmarks are identified, the presence of these landmarks can be employed for classification of the given frame into various classes of severity of infection in lung. The proposed framework has been trained on 130 LUS videos and validated on 100 LUS videos acquired from multiple centres at Spain and India. Frames were independently assessed by experts to identify clinically relevant features such as A-lines, B-lines, and pleura in LUS videos. The key points detected showed high sensitivity of 99% in detecting the image landmarks identified by experts. Also, on employing for classification of the given lung image into normal and abnormal classes, the proposed approach, even with no prior training, achieved an average accuracy of 97% and an average F1-score of 95% respectively on the task of co-classification with 3-fold cross-validation.

Unsupervised Multi-Latent Space RL Framework for Video Summarization in Ultrasound Imaging.

The COVID-19 pandemic has highlighted the need for a tool to speed up triage in ultrasound scans and provide clinicians with fast access to relevant information. To this end, we propose a new unsupervised reinforcement learning (RL) framework with novel rewards to facilitate unsupervised learning by avoiding tedious and impractical manual labelling for summarizing ultrasound videos. The proposed framework is capable of delivering video summaries with classification labels and segmentations of key landmarks which enhances its utility as a triage tool in the emergency department (ED) and for use in telemedicine. Using an attention ensemble of encoders, the high dimensional image is projected into a low dimensional latent space in terms of: a) reduced distance with a normal or abnormal class (classifier encoder), b) following a topology of landmarks (segmentation encoder), and c) the distance or topology agnostic latent representation (autoencoders). The summarization network is implemented using a bi-directional long short term memory (Bi-LSTM) which utilizes the latent space representation from the encoder. Validation is performed on lung ultrasound (LUS), that typically represent potential use cases in telemedicine and ED triage acquired from different medical centers across geographies (India and Spain). The proposed approach trained and tested on 126 LUS videos showed high agreement with the ground truth with an average precision of over 80% and average F1 score of well over 44 ±1.7 %. The approach resulted in an average reduction in storage space of 77% which can ease bandwidth and storage requirements in telemedicine.

Should all tubercular cavities be left alone? Lessons from a heart transplant.

Fungal infection after solid organ transplantation poses a diagnostic and therapeutic challenge. We present the case of a 50-year-old man who underwent orthotopic heart transplantation for dilated cardiomyopathy with a history of treated pulmonary tuberculosis 10 years pre-transplant. One year post-transplantation, he was admitted with recurrent productive cough and was evaluated to have intracavitory aspergillosis of the lung. He was started on medical therapy with reduction in immunosuppression, but succumbed later with allograft rejection and multiorgan failure. Management of invasive aspergillosis in immunocompromised host is a real challenge. Management protocol should be individualised.

"Not all bullae are synonymous with COPD"-a rare congenital anomaly described.

Hyperlucent areas with thin walls and absent vascular markings in chest X ray are described as radiological findings of a bullae. We present the case of an adult male referred for coronary revascularisation and bullectomy in the right lung. A non-smoker, without any significant past medical history, made us think of bronchial atresia. He was planned for coronary artery bypass grafting with close follow-up of lung anomaly. Clinicians should be aware of this entity in non-smokers with unilateral bullous lesion and calcification as other close clinical differentials warrant aggressive medical management.

Brucellosis After Cardiac Transplantation.

Brucellosis is being increasingly recognized after solid organ transplantation but has not been reported after orthotopic heart transplantation. We present the case of a 51-year-old farmer who underwent orthotopic heart transplantation and was readmitted after 3 months in a severely immunosuppressed state with significant nonspecific complaints. He posed a diagnostic and management dilemma to all disciplines, but finally turned out to be harboring Brucella infection. He responded well to medical management and was discharged in a stable clinical status. Although rare, brucellosis should be included in the investigative workup for nonspecific symptoms after cardiac transplantation.

Role of Pirfenidone in Idiopathic Pulmonary Fibrosis - A Longitudinal Cohort Study.

BACKGROUND: But so far there is no proven pharmacological treatment for Idiopathic pulmonary fibrosis (IPF). As trials investigating different agents with different mechanisms of actions are going on, encouraging results have led to the licensing of the first IPF-specific drug, Pirfenidone. OBJECTIVE: To assess the proportion of IPF among interstitial lung disease patients and to assess their treatment response to Pirfenidone. MATERIAL AND METHODS: All consecutive patients attending the outpatient department from 1st January 2012 to 30th June 2012 with a proven diagnosis of Interstitial lung Disease (ILD) were included in this longitudinal cohort study. Out of the total ILDs, patients with IPF were identified. The disease, its natural course, available treatment options and the risks and benefits of drugs were discussed with each IPF patient along with their family members. After obtaining their consent, we started 23 patients on a combination of Pirfenidone, N-acetyl cysteine (NAC) and proton pump inhibitors (PPI). Patients were followed up for 52 weeks. Pirfenidone was discontinued in one patient due to an adverse effect 1 month after onset of treatment. Anova test using SPSS software and independent T test was used to analyse the data. RESULTS: During the study period 69 patients with ILD attended our OPD which included 24 IPF patients representing 34.8% and 23 of these patients received treatment with Pirfenidone, NAC and PPI. One patient discontinued Pirfenidone due to adverse effects. After 12 months, 8 patients had worsening of FVC ≥10%, the FVC of 7 patients remained stable, 8 patients could not repeat the tests and none of them had improvement. There was less than 15% decline in DLCO for 9 patients, 7 patients could not repeat the test and none improved. 8 patients had stable dyspnoea on exertion and 11 had worsening. Three patients died. Combining all the above parameters, only 4 patients had stable disease with the rest having no improvement. CONCLUSIONS: The present study does not show any significant beneficial effect for Pirfenidone. Only four patients remained stable which cannot be attributed to the effect of any particular management strategy.

Diffuse Parenchymal Lung Diseases with Clinicoradiological Discordance: Role of Transbronchial Lung Biopsy as a Diagnostic Tool - An Observational Study.

INTRODUCTION: The diagnosis of Diffuse Parenchymal Lung Disease (DPLD) requires a multidisciplinary approach with reconciliation of clinicoradiological and histopathological data. But when the preliminary clinicoradiological profile fails to suggest a diagnosis, an adequate lung biopsy specimen with meticulous histological examination and a multidisciplinary approach usually yields results. There is also a high chance of sampling error due to patchy and heterogeneous involvement of the disease process and due to the small volume of tissue taken. As seen in our study, Trans-Bronchial Lung Biopsy (TBLB) if performed by an experienced bronchoscopist can be done as an outpatient procedure yielding adequate specimens for diagnosis and guide effective treatment in these patients. AIM: To study the utility and diagnostic yield of TBLB in DPLD patients when there is clinicoradiological discordance. MATERIALS AND METHODS: The current retrospective observational study was undertaken in the Institute of Chest Diseases, Government Medical College, Kozhikode, Kerala, India, from January 2012 to December 2014. Out of 169 DPLD patients who attended the tertiary care centre, 66 patients without a definite diagnosis by clinicoradiological assessment were included in the study. They underwent TBLB using a fibre-optic video bronchoscope. An open lung biopsy was advised if the TBLB did not yield a definite diagnosis. RESULTS: Among the 66 patients, histopathological confirmation was obtained in 51 patients, 39 of which were by TBLB (59%). Few diagnoses like invasive adenocarcinoma, Pneumocystis jirovecii pneumonia and Aspergillus infection were least expected. CONCLUSION: TBLB if performed correctly can be an effective intervening modality in establishing the diagnosis of DPLD before going for an invasive surgical biopsy.